LLM Torch Profiler Analysis

Unified LLM torch-profiler triage skill for `sglang`, `vllm`, and `TensorRT-LLM`. Use it to inspect an existing `trace.json(.gz)` or profile directory, or to drive live profiling against a running server and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.

kunpengcompute Updated

File contents

kunpengcompute/sglang commit 24fac5dddc

Frequently asked questions

npx get-skill add kunpengcompute/llm-torch-profiler-analysis